@aeondave/pi-skill-optimizer
Less repeated context for Pi: local skill routing, on-demand tools, and recoverable output reduction.
Package details
Install @aeondave/pi-skill-optimizer from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:@aeondave/pi-skill-optimizer- Package
@aeondave/pi-skill-optimizer- Version
3.2.1- Published
- Nov 18, 2026
- Downloads
- 432/mo · 239/wk
- Author
- aeondave
- License
- MIT
- Types
- extension
- Size
- 2.1 MB
- Dependencies
- 0 dependencies · 4 peers
Pi manifest JSON
{
"image": "https://raw.githubusercontent.com/AeonDave/pi-skill-optimizer/v3.2.1/assets/banner.png",
"extensions": [
"./src/index.ts"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
pi-skill-optimizer
Keep your skill library. Cut the repeated context.

An extension for Pi that makes room for your work by reducing repeated skill descriptions, tool definitions, and large results. Keep a growing library available without carrying all of it through every request.
Pi chooses what to use in the context of your task. The optimizer makes that choice easier to navigate and keeps the original instructions and results within reach.
More capability, less repeated context
- A library Pi can explore. Optional setup turns skill descriptions into a compact topic directory and browsable cards. Pi can find a specialist, discover a supporting method, or load a known skill's full instructions and resources directly.
- Tools that follow the work. Tool definitions become available through search as the task develops. Core tools and tools already in use remain active within the host's permissions.
- Shorter results with a way back. Large output can be reduced with a link to its complete local original. Later exact duplicates can reuse that original, while the first result stays intact.
- Progress you can see. Search results have compact, expandable cards. Setup shows live progress, and status explains readiness, savings, provider usage, and the outcome of the last request.
Install
Requires Pi 1.0.1+ and Node.js 26.3+.
pi install npm:@aeondave/pi-skill-optimizer
Restart Pi, then check the optimizer's status:
/skill-optimizer
The defaults work immediately. See installation and updates for other install options and upgrades.
Give Pi a map of your library
Run the optional setup to organize your installed skills into browsable topics:
/skill-optimizer init
Init uses your current Pi model and may incur provider cost. A panel above the editor shows saved progress, the current batch and model, elapsed time, and provider activity while it works.
Completed batches are saved as they finish. You can stop with:
/skill-optimizer cancel
Run init again to finish missing work or refresh changed skills. Your source skills stay unchanged. Everyday discovery runs locally without an embedding service or a separate ranking model; Pi's main model chooses what to load. Without init, Pi still gets a compact index of the available skills.
Keep working as usual
Ask Pi to do your work. AUTO manages discovery and result size in the background, respects the host's selected skills and tools, and preserves instructions preloaded by pi-persona or another extension.
Use /skill-optimizer to see what is happening, or /skill-optimizer audit to find description issues in your library without rewriting it.
Start with the defaults; configuration covers project preferences, output modes, RTK coexistence, and persona restrictions.
Understand the trade-offs
On-demand discovery trades repeated context for occasional browsing turns. The benefit depends on your library and how Pi uses it; benchmarks and evaluation limits give measured examples and explain their scope.
Reduced results keep their originals in local archives for seven days by default. Normal hooks do not collect a benchmark corpus. See privacy and persistence before changing retention or running an explicit remote evaluation.
Explore further
- Configuration and command reference — setup, controls, and everyday troubleshooting.
- How AUTO works — discovery, dynamic tools, output recovery, and guarantees.
- Ranking decisions — selection behavior and relevance limits.
- Benchmark protocol — measurements, local validation, and private evaluation workflows.
- Changelog — release history.
MIT. See LICENSE.
